Re: TLB and PTE coherency during munmap

[Max Filippov <jcmvbkbc@gmail.com>]

Hi Peter,

On Wed, May 29, 2013 at 9:51 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> What about something like this?

With that patch I still get mtest05 firing my TLB/PTE incoherency check
in the UP PREEMPT_VOLUNTARY configuration. This happens after
zap_pte_range completion in the end of unmap_region because of
rescheduling called in the following call chain:

unmap_region
  free_pgtables
    unlink_anon_vmas
      lock_anon_vma_root
        down_write
          might_sleep
            might_resched
              _cond_resched


>
> ---
>  include/asm-generic/tlb.h | 11 ++++++++++-
>  mm/memory.c               | 17 ++++++++++++++++-
>  2 files changed, 26 insertions(+), 2 deletions(-)
>
> diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
> index b1b1fa6..651b1cf 100644
> --- a/include/asm-generic/tlb.h
> +++ b/include/asm-generic/tlb.h
> @@ -116,6 +116,7 @@ struct mmu_gather {
>
>  static inline int tlb_fast_mode(struct mmu_gather *tlb)
>  {
> +#ifndef CONFIG_PREEMPT
>  #ifdef CONFIG_SMP
>         return tlb->fast_mode;
>  #else
> @@ -124,7 +125,15 @@ static inline int tlb_fast_mode(struct mmu_gather *tlb)
>          * and page free order so much..
>          */
>         return 1;
> -#endif
> +#endif /* CONFIG_SMP */
> +#else  /* CONFIG_PREEMPT */
> +       /*
> +        * Since mmu_gather is preemptible, preemptible kernels are like SMP
> +        * kernels, we must batch to make sure we invalidate TLBs before we
> +        * free the pages.
> +        */
> +       return 0;
> +#endif /* CONFIG_PREEMPT */
>  }
>
>  void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
> diff --git a/mm/memory.c b/mm/memory.c
> index 6dc1882..e915af2 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -384,6 +384,21 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
>
>  #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
>
> +static inline void cond_resched_tlb(struct mmu_gather *tlb)
> +{
> +#ifndef CONFIG_PREEMPT
> +       /*
> +        * For full preempt kernels we must do regular batching like
> +        * SMP, see tlb_fast_mode(). For !PREEMPT we can 'cheat' and
> +        * do a flush before our voluntary 'yield'.
> +        */
> +       if (need_resched()) {
> +               tlb_flush_mmu(tlb);
> +               cond_resched();
> +       }
> +#endif
> +}
> +
>  /*
>   * If a p?d_bad entry is found while walking page tables, report
>   * the error, before resetting entry to p?d_none.  Usually (but
> @@ -1264,7 +1279,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
>                         goto next;
>                 next = zap_pte_range(tlb, vma, pmd, addr, next, details);
>  next:
> -               cond_resched();
> +               cond_resched_tlb(tlb);
>         } while (pmd++, addr = next, addr != end);
>
>         return addr;
>
>



-- 
Thanks.
-- Max